Cascade, an LLM serving system that estimates and continuously updates this per-request latency budget from request characteristics, KV-cache state, and current system load, and uses a single per-request budget to jointly coordinate request scheduling and KV-cache management across the memory hierarchy.
Abstract
The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests. LLM serving platforms today define response-latency service-level objectives, even though requests within the same service can differ by orders of magnitude in input length, generation length, execution cost, and the availability of reusable KV-cache state. As a result, requests governed by the same service level objective have different urgency: after accounting for the time required to execute them, some have substantial latency headroom while others have almost none. We define this headroom---the difference between a request's service level objective and its predicted remaining service time---as its per-request latency budget. We present Cascade, an LLM serving system that estimates and continuously updates this budget from request characteristics, KV-cache state, and current system load. Unlike prior SLO-aware schedulers that use deadlines to govern request ordering alone, Cascade uses a single per-request budget to jointly coordinate request scheduling and KV-cache management across the memory hierarchy. Its scheduler prioritizes requests with little remaining budget, while its memory manager uses the same budget to decide whether non-resident KV state should be restored or prefetched from a deeper tier, retained in HBM, or recomputed. By directing queueing and data-movement overhead toward requests that can absorb it, Cascade improves SLO-satisfied goodput while preserving fairness across heterogeneous request classes. On production traces across three large language models, Cascade improves goodput by up to2.4x and reduces SLO violations by 40% relative to the default vLLM first-come, first-served scheduler.
CELLServe formalizes SLO-constrained joint resource provisioning as an optimization problem with a dedicated algorithm, and introduces an opportunistic instance merging strategy for decode phase functions to reclaim fragmented resources.
Zejian Wang, Nan Lin, Zinuo Cai et al.· ACM Transactions on Architec...· 0 citations
Long-context LLM applications such as retrieval-augmented generation (RAG) and agentic systems often process tens of thousands of input tokens to produce short outputs, making end-to-end request latency an important serving objective. We show that the maximum number of batched tokens (MBT), which controls the token scheduling budget in vLLM, has a scheduling-pressure-dependent effect on latency. Larger token budgets can reduce latency under low scheduling pressure, while smaller budgets become preferable under higher pressure. Consequently, no single static MBT performs best across load regimes. We introduce Prefill-Pressure Adaptive Scheduling (P-PAS), a lightweight policy that dynamically adapts the scheduling budget based on concurrent prefill and decode state. P-PAS retains a large token budget under low pressure and constrains prefill work as pressure increases. Across models, workloads, and GPUs, P-PAS maintains low end-to-end latency across changing load regimes, avoiding the limitations of a fixed MBT. Kernel-level profiling shows that large prefill chunks can improve execution efficiency under low scheduling pressure, but that this advantage varies across model--hardware configurations. As scheduling pressure increases, smaller chunks can instead reduce interference with active decoding, explaining the observed load-dependent MBT sensitivity. Code and artifacts for reproducing our results are available at https://github.com/TimoSaemann/ppas-vllm .
The rapid proliferation of Large Language Models (LLMs) with varying capability profiles, context window limits, execution latencies, and financial costs presents a significant operational challenge for enterprise AI deployments. Monolithic deployment strategies wherein all requests are directed to a single high-capability frontier model result in substantial compute over-provisioning and excessive operational costs for routine queries. Conversely, relying solely on lightweight models degrades output accuracy on complex multi-step reasoning tasks. To resolve this trade-off, this paper introduces LLM-Advisor, an open-source, adaptive framework designed for intelligent query categorization, dynamic model evaluation, and constraint-aware request routing across heterogeneous multi-LLM pools. LLM-Advisor analyzes incoming prompt features, structural complexity, domain requirements, and user-defined constraints (e.g., maximum cost per request, latency thresholds) to route tasks to the optimal candidate model. We evaluate LLM-Advisor using a benchmark suite of 1,000 queries across code generation, general reasoning, and contextual retrieval tasks using both proprietary and open-weight models (including GPT-4o, Claude 3.5 Sonnet, Llama 3, and Mistral). Experimental results demonstrate that LLM-Advisor achieves a 42% reduction in overall inference expenditure and a 35% decrease in average response latency while retaining 94.6% task accuracy compared to static GPT-4o baseline routing. These findings highlight LLM-Advisor as an efficient, highly scalable middleware solution for production-grade AI system deployments.
Harshil Lodhiya· International Journal of Res...· 0 citations
Modern LLM serving deployments must simultaneously satisfy heterogeneous service-level objectives (SLOs) across a diverse population of user tiers, ranging from latency-critical API calls to background batch processing. Llumnix introduced a dynamic, migration-capable multi-instance scheduler for LLM inference that achieves load balancing, defragmentation, prioritization, and auto-scaling through a unified"freeness"metric. However, Llumnix's priority model is restricted to two levels (high and normal), an abstraction too coarse to express the richer SLA classes common in production deployments. In this work, we extend Llumnix's priority model to support an arbitrary number of tiers and evaluate the effects of this extension under three realistic priority distributions (uniform, Gaussian, enterprise) using Vidur, a high-fidelity LLM inference simulator. We implement per-tier headroom with exponential decay, tier-aware dispatch ordering, and the full Llumnix migration pipeline inside Vidur's hierarchical scheduling framework. We compare our extended scheduler against INFaaS (global routing baseline), vLLM, Orca, and Sarathi-Serve (per-replica baselines), sweeping priority levels from 1 to 10. Our experiments demonstrate that four priority tiers yields the best cost-effectiveness tradeoff, achieving prefill mean speedups of up to 8.3x and end-to-end P99 speedups of up to 3.1x over INFaaS with cost-per-latency improvements of 46 to 68%, while preserving strong SLO differentiation across tiers. We further show that the system sustains these gains at 10 priority levels without tail latency collapse, with overhead concentrated in the prefill phase.
Anders Vestrum, Arya Raeesi, Hanna Roed· 0 citations
Recent LLM-based agent systems continuously accumulate context across multi-turn interactions, tool invocations, and cross-session workflows. Replaying the full history for every request quickly becomes impractical: long contexts increase prefill cost, may exceed context limits, and often bury task-relevant evidence in irrelevant content, degrading both serving efficiency and output quality. We propose Akashic, a low-overhead memory system built around MemAttention, which organizes context into bounded chunks and models semantic relationships across chunks, preserving cross-chunk evidence without repeatedly rewriting the full history. Akashic further applies hardware-software co-designed memory placement to co-locate likely co-retrieved chunks, reducing retrieval fragmentation and I/O overhead. Across four representative workloads and three model sizes, Akashic improves task accuracy by up to 10.2 points, throughput by up to 1.21x, and sustainable request rate by up to 1.88x over strong prior memory baselines.
Yang Liu, ZhaoKai Luo, Huayi Jin et al.· 0 citations
LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a host-agnostic co-serving design that converts this idle inference capacity into LoRA fine-tuning throughput while preserving inference service-level objectives (SLOs). DeltaServe integrates with existing inference engines through a compact hook interface that requires only multi-LoRA batching support. It exploits the shared execution structure of inference prefill and LoRA fine-tuning forward passes, and uses an SLO-aware scheduler to admit and execute fine-tuning only when sufficient inference headroom is available. The scheduler is driven by a CUDA-graph-aware latency model calibrated offline and refined online. We integrate DeltaServe with vLLM, SGLang, and S-LoRA. On a production trace from Company X, DeltaServe on vLLM delivers 2.9x higher fine-tuning throughput than LLMStation at 100% inference SLO compliance, versus 85% for LLMStation. It also achieves 39% higher fine-tuning throughput than a baseline running vLLM+torchtune, using no additional hardware and maintaining full SLO compliance.
Jiaxuan Chen, Jianshu She, Ye Yuan et al.· 0 citations